TY - JOUR
T1 - A Primer on the Present State and Future Prospects for Machine Learning and Artificial Intelligence Applications in Cardiology
AU - Manlhiot, Cedric
AU - van den Eynde, Jef
AU - Kutty, Shelby
AU - Ross, Heather J.
N1 - Funding Information:
We thank Grace Howard and Madeline Cheshire for their contribution to the literature review. Jef van den Eynde is supported by the Belgian American Educational Foundation.
Funding Information:
We thank Grace Howard and Madeline Cheshire for their contribution to the literature review. Jef van den Eynde is supported by the Belgian American Educational Foundation. The authors have no funding sources to declare. Dr Kutty is a consultant for GE Healthcare. The other authors have no conflicts of interest to disclose.
Publisher Copyright:
© 2021 Canadian Cardiovascular Society
PY - 2022/2
Y1 - 2022/2
N2 - The artificial intelligence (AI) revolution is well underway, including in the medical field, and has dramatically transformed our lives. An understanding of the basics of AI applications, their development, and challenges to their clinical implementation is important for clinicians to fully appreciate the possibilities of AI. Such a foundation would ensure that clinicians have a good grasp and realistic expectations for AI in medicine and prevent discrepancies between the promised and real-world impact. When quantifying the track record for AI applications in cardiology, we found that a substantial number of AI systems are never deployed in clinical practice, although there certainly are many success stories. Successful implementations shared the following: they came from clinical areas where large amount of training data was available; were deployable into a single diagnostic modality; prediction models generally had high performance in external validation; and most were developed as part of collaborations with medical device manufacturers who had substantial experience with implementation of new clinical technology. When looking into the current processes used for developing AI-based systems, we suggest that expanding the analytic framework to address potential deployment and implementation issues at project outset will improve the rate of successful implementation, and will be a necessary next step for AI to achieve its full potential in cardiovascular medicine.
AB - The artificial intelligence (AI) revolution is well underway, including in the medical field, and has dramatically transformed our lives. An understanding of the basics of AI applications, their development, and challenges to their clinical implementation is important for clinicians to fully appreciate the possibilities of AI. Such a foundation would ensure that clinicians have a good grasp and realistic expectations for AI in medicine and prevent discrepancies between the promised and real-world impact. When quantifying the track record for AI applications in cardiology, we found that a substantial number of AI systems are never deployed in clinical practice, although there certainly are many success stories. Successful implementations shared the following: they came from clinical areas where large amount of training data was available; were deployable into a single diagnostic modality; prediction models generally had high performance in external validation; and most were developed as part of collaborations with medical device manufacturers who had substantial experience with implementation of new clinical technology. When looking into the current processes used for developing AI-based systems, we suggest that expanding the analytic framework to address potential deployment and implementation issues at project outset will improve the rate of successful implementation, and will be a necessary next step for AI to achieve its full potential in cardiovascular medicine.
UR - http://www.scopus.com/inward/record.url?scp=85122266625&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85122266625&partnerID=8YFLogxK
U2 - 10.1016/j.cjca.2021.11.009
DO - 10.1016/j.cjca.2021.11.009
M3 - Review article
C2 - 34838700
AN - SCOPUS:85122266625
SN - 0828-282X
VL - 38
SP - 169
EP - 184
JO - Canadian Journal of Cardiology
JF - Canadian Journal of Cardiology
IS - 2
ER -